Identification of hypertension subtypes using microRNA profiles and machine learning
Authors' conclusion
This study confirms the potential of circulating miRNAs to serve as diagnostic biomarkers for EHT and the viability of ML as a tool for identifying the most informative miRNA species.
Study context
- Population
- Patients with primary hypertension (PHT) or endocrine hypertension (EHT: Primary aldosteronism (PA), Cushing's syndrome (CS), PPGL)
- Comparison
- Circulating microRNA (miRNA)-based machine learning (ML) classification of EHT and its subtypes vs PHT
- Outcome
- Classification vs PHT (test set)
Methodological detailssupervised machine learning (8 methods), test set
- Supervised machine learning (8 methods)
- Test set
Performance
As reported in the abstract
AUC, PPGL vs PHT
0.9
AUC, CS vs PHT
0.9
AUC, EHT vs PHT
0.9
AUC, PA vs PHT
0.8
Further findings
Most prominent circulating miRNA features
- Most prominent miRNA features across disease combinations: hsa-miR-15a-5p and hsa-miR-32-5p
Original publication
Identification of hypertension subtypes using microRNA profiles and machine learning. Eur J Endocrinol. Published 19 March 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →